Glossary term
Glossary term
Foundations
Overloaded term having any of the following definitions:
The number of levels of coordinates in a Tensor. For example:
A scalar has zero dimensions; for example, ["Hello"].
A vector has one dimension; for example, [3, 5, 7, 11].
A matrix has two dimensions; for example, [[2, 4, 18], [5, 7, 14]]. You can uniquely specify a particular cell in a one-dimensional vector with one coordinate; you need two coordinates to uniquely specify a particular cell in a two-dimensional matrix.
The number of entries in a feature vector.
The number of elements in an embedding layer.
Created for this library
An embedding team selects 768 dimensions for its sentence encoder to balance representation quality against storage cost in the vector index.
A retail recommendation team trades dimensions for inference speed when picking the user-embedding size that fits its serving latency budget.
A search team benchmarks embedding dimensions from 128 to 1,024 to find the smallest size that maintains retrieval quality on its evaluation set.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License